© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3569
    Prev
    Next
    INDEX
    Explanations

    the word "thing."

    oai_token-act-pair · gemini-2.0-flash

    thing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     thing
    -0.83
     commerciale
    -0.59
     commerciali
    -0.59
     area
    -0.58
     way
    -0.54
     coisa
    -0.53
     commerciales
    -0.53
     lettere
    -0.52
    ↵↵
    -0.52
     guy
    -0.52
    POSITIVE LOGITS
    Autoritní
    0.77
    utilisons
    0.73
    ">:
    0.71
    )​
    0.69
     wireType
    0.68
    Portale
    0.68
    expandindo
    0.66
    
    0.66
    GETHER
    0.66
    ^(@)
    0.65
    Activations Density 0.916%

    No Known Activations